菜单
Use when AI contribution metadata must match the actual workflow, when model alias and dated identifiers need auditing, when verified and fabricated citation counts feed a release decision, or when a venue's AI disclosure statement needs evidence behind it.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | ai-disclosure-auditor |
| description | Use when AI contribution metadata must match the actual workflow, when model alias and dated identifiers need auditing, when verified and fabricated citation counts feed a release decision, or when a venue's AI disclosure statement needs evidence behind it. |
Use this skill before release, after AI-assisted drafting, or during citation cleanup when the user needs disclosure metadata to match the actual workflow. Its citation counts come from apa-doi-verifier results, and its verdict feeds repo-release-integrity-check at release time. It is not for building an open-science release package or recording authorship contributions, those are open-science-release-packager and authorship-contribution-ledger.
ai_assisted reflects actual AI use.ai_tools.name, vendor, model_alias, model_dated, and role.human_review and human_review_date.verified_citations_count with the reference list and in-text citation set when available.fabricated_citations_count is zero for release material.disclosure_standard against the current project policy.Return:
Do not expose prompts, logs, private notes, credentials, unpublished clinical data, or reviewer identities unless the user explicitly supplies publication-safe excerpts. Keep the audit at metadata and disclosure level when private context is not needed.
"Audit the AI disclosure fields for all released booklets and tell me which files block v1.1.0."
Expected smoke output:
Bu beceri, yapay zekâ katkı beyanının gerçek iş akışıyla örtüşüp örtüşmediğini alan alan denetler. Model kimlikleri, insan incelemesi durumu ve atıf sayıları kanıtla karşılaştırılır, uydurma atıf içeren içerik yayına kapatılır. Atıf sayıları apa-doi-verifier doğrulamasından gelir, sonuç yayın bütünlüğü kontrolüne girdi olur. Açık bilim paketi için open-science-release-packager'a, yazarlık katkı kaydı için authorship-contribution-ledger'a devredilir. Oturum sonunda denetim kararı ve bekleyen alanlar kayda geçirilir.
Use when a complete research workflow — its instructions, skills, data boundaries, and tool connections — must be assessed for portability across AI agents or environments, so each component is explicitly mapped before migration rather than assumed to transfer.
Use when a Claude Code session loops, drifts from scope, claims a fix that CI rejects, hits context, PATH, or permission walls, or fails in a way another retry will not solve and a root cause diagnosis is needed instead.
Use when a draft in Turkish, English, or both reads as AI-generated and needs revision that removes machine writing patterns and translation calques while preserving meaning, citations, statistics, and the author's voice.
Use when a reference list needs APA 7 cleanup, when DOIs must be confirmed real against Crossref or PubMed, when the user asks whether AI-suggested citations actually exist, or when a manuscript needs a citation hygiene pass before submission or defense.
Use when authorship order, CRediT contribution roles, or AI-assistance attribution must be recorded transparently for a manuscript, when an author dispute needs an evidence trail, or before a contributorship statement is required at submission; this skill maintains the human-attribution ledger of who contributed what and in which role (authorship order, CRediT taxonomy, revision responsibilities), which is distinct from the disclosure-metadata audit owned by ai-disclosure-auditor.
Use when paired tr.md and en.md files need a parity verdict, when titles, frontmatter, headings, or DOI sets may have drifted between languages, or when a bilingual document is approaching release and its translation coverage needs an audit.